Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tyler-R-Kendrick/agent-skills --skill improvegit clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve)<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/improve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00215 | $0.02113 |
| Opus 5 | $0.00108 | $0.01056 |
| Sonnet 5 | $0.00043 | $0.00423 |
| Haiku 4.5 | $0.00021 | $0.00211 |
Grade A, and why
improve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evals and Self-Improvement Pipelines
Operating Rule
Default new agent and LLM evals to AgentEvals EVAL.yaml with AgentV. Improve only against evidence: eval failures, trace observations, benchmark deltas, human review notes, or explicit user goals. Keep each loop narrow, reproducible, and auditable.
Progressive Disclosure
Load only the reference needed for the requested eval or improvement surface:
| If the task says... | Then read... |
|---|---|
| "install", "setup", "environment", "venv", "dependencies", "API keys", "Node", "Python", or missing native tools | references/environment-setup.md |
| "install AgentV", "install ASSERT", "setup eval tools", "eval runner install", or native eval validation setup | references/install-eval-tools.md |
| "install GEPA", "install Trace", "install Agent Lightning", "install SkillOpt", "setup optimizer", or improvement library dependencies | references/install-improvement-libs.md |
| "create an eval", "judge", "grader", "rubric", "EVAL.yaml", or no eval standard | references/agentevals.md and references/agentv.md |
| "which eval standard", "convert eval", "compare standards", or mixed eval formats | references/eval-standards-guide.md |
"Agent Skills eval", evals.json, "skill quality", "with_skill", or "without_skill" |
references/agent-skills-evals.md |
"ASSERT", assert-ai, "judge-traces", "spec-driven", "behavior taxonomy", "trace-aware", "policy failure modes", or eval_config.yaml |
references/assert.md |
| "eval starter", "eval lint", "eval workspace contract", or expected eval artifacts | references/eval-workspace-contracts.md |
| "optimize a skill", "progressive disclosure", "Table of Contents", "Index Page", "conditional access", "top-level links", "scripted workflow", or "deterministic workflow generation" | references/skill-optimization-strategy.md |
| "which technique", "optimize this", "improvement plan", or mixed artifacts | references/techniques-guide.md |
| "GEPA", "Pareto", "reflective mutation", "prompt evolution", or "optimize anything" | references/gepa.md |
| "Trace", "OptoPrime", "computation graph", "node", "bundle", or end-to-end generative optimization | references/microsoft-trace.md |
| "VISTA", "interpretable APO", "hypothesis agent", "random restart", or "epsilon-greedy" | references/vista.md |
| "Agent Lightning", "RL", "reward", "policy reward", "governed training", or skill improvement with policy constraints | references/agent-lightning.md |
"SkillOpt", "SkillOpts", "skill evolution", best_skill.md, "held-out gate", "bounded edits", "textual learning rate", or "SkillOpt-Sleep" |
references/skillopt.md |
| "eval failures", "agent traces", "span logs", "benchmark deltas", or "release evidence" | references/eval-trace-improvement.md |
| "synthetic data", "simulation data", "Simula", "QDC", "Source2Synth", "MAG-V", "MetaSynth", "BARE", "Condor", "data auditor", "generate data", or "simulate" | references/simulation-data.md |
| "CLI", "init", "improve", "eval", "simulate", "lint", "workspace", or "deterministic improvement artifacts" | references/workspace-contracts.md |
What ships with it
44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 7.6 KB
- metadata.json 611 B
- README.md 815 B
- references/agent-lightning.md 5.0 KB
- references/agent-skills-evals.md 3.0 KB
- references/agentevals.md 3.8 KB
- references/agentv.md 2.8 KB
- references/assert.md 7.8 KB
- references/environment-setup.md 3.4 KB
- references/eval-standards-guide.md 3.2 KB
- references/eval-trace-improvement.md 3.1 KB
- references/eval-workspace-contracts.md 3.3 KB
- references/gepa.md 2.5 KB
- references/install-eval-tools.md 4.3 KB
- references/install-improvement-libs.md 6.4 KB
- references/microsoft-trace.md 3.0 KB
- references/simulation-data.md 10 KB
- references/skill-optimization-strategy.md 5.4 KB
- references/skillopt.md 6.0 KB
- references/techniques-guide.md 5.6 KB
- references/vista.md 4.2 KB
- references/workspace-contracts.md 11 KB
- rules/_sections.md 2.0 KB
- rules/_template.md 366 B
- rules/improve-codify-workflows-in-scripts.md 547 B
- rules/improve-design-synthetic-data-before-sampling.md 584 B
- rules/improve-from-evidence.md 516 B
- rules/improve-keep-loops-narrow.md 456 B
- rules/improve-prefer-deterministic-checks.md 502 B
- rules/improve-preserve-baselines.md 463 B
- rules/improve-record-rejected-paths.md 491 B
- rules/improve-use-agentevals-by-default.md 518 B
- rules/improve-use-gepa-for-text-evolution.md 484 B
- rules/improve-use-progressive-disclosure-by-default.md 545 B
- rules/improve-use-trace-for-trainable-workflows.md 521 B
- rules/improve-use-vista-for-interpretability.md 515 B
- rules/improve-validate-natively-first.md 529 B
- rules/improve-validate-the-candidate.md 509 B
- rules/improve-wire-explicit-assertions.md 487 B
- scripts/improve-cli.test.ts 17 KB runs code
- scripts/improve-cli.ts 100 KB runs code
- scripts/simulation-lib.ts 17 KB runs code
- scripts/techniques-lib.ts 17 KB runs code
- scripts/vista-lib.ts 23 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 106 lines · 215 tokens per session scan A 1112baffb20e
improve is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 215 tokens to every session and 2,113 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.